Problems / Agents and tools, medium
A data-analysis agent runs Python in sandboxes: 6 sandboxes, about 1.2 s per run, 4 runs per task at 2 tasks a second.
Free to open. Runs in your browser, no sign-up.
Success ≥ 95% of tasks, p99 ≤ 90 s.
2 requests a second for 45 seconds: 100% task (writes).
What each component does in this design, and what calls it. The simulator mimics each one from these settings.
| Component | Its job here | Settings |
|---|---|---|
| Load balancerLoad balancer | Traffic enters here.Calls Agent API.Layer 4 balancers route by IP and port; layer 7 balancers read HTTP and can route by path or header. | – |
| Agent APIApp service | Load balancer forwards to it.Calls Agent orchestrator.Little's law: throughput ≈ concurrency ÷ latency. 200 slots at 50 ms serve about 4,000 req/s. | 3 replicas × 500 slots · timeout 180 s |
| Agent orchestratorAgent orchestrator | Agent API calls it.Calls Model, Code sandbox.An agent loops: think, call a tool, read the result, repeat until done. | 400 slots · 4 steps |
| ModelLLM endpoint | Agent orchestrator calls it.Latency has two parts: time to the first token, then a steady stream of tokens per second. | 300 streams |
| Code sandboxCode sandbox | Agent orchestrator calls it.Sandboxes run model-written code in an isolated container with limited network and time. | 6 slots |
Try it first. Open one hint at a time if you get stuck.
8 runs a second × 1.2 s ≈ 10 sandboxes busy.
Agent work multiplies: tasks a second × steps per task = calls a second on every tool the loop uses.
Add sandbox capacity (and keep a warm pool).